This is Spanish Voxforge acoustic model for CMUSphinx decoders -
pocketsphinx and sphinx4 version 0.1. It was trained with SphinxTrain.
The process of training is described in SphinxTrain tutorial.

This is 8kHz model, it could be used both for desktop and telephone
recordings.

To setup the files use build.sh script from scripts folder as a base. It
should download required files from Voxforge, setup structure and
extract features. Scripts are located in scripts subfolder.

Testing is performed with pocketsphinx. Language model for testing is built
from test prompts with SRILM. Result of the testing should be similar to

TOTAL Words: 5585 Correct: 5333 Errors: 269
TOTAL Percent correct = 95.49% Error = 4.82% Accuracy = 95.18%
TOTAL Insertions: 17 Deletions: 178 Substitutions: 74

If you need serious language model you can build it yourself from your texts
or from public corporas like Wikipedia dump.

To use this model with pocketsphinx, just provide it's location with
-hmm pocketsphinx option.For information on how to use this model with
sphinx4 see the documentation

http://cmusphinx.sourceforge.net/sphinx4/doc/UsingSphinxTrainModels.html

Remember that this model uses MLLT and it requires both frontend
modification. You need to use transform with LDA component and you need
to adjust melfilter parameters.

===== Revision Log =====

0.1.1

Updated Spanish phonetic dictionary. Previous was too heavy Mexican. Thanks to
Guillermo Perez <g.perez@indisys.es>.
